Login / Signup
On dynamic programming for sequential decision problems under a general form of uncertainty.
Paolo Dai Pra
Wolfgang J. Runggaldier
Cristina Rudari
Published in:
Math. Methods Oper. Res. (1997)
Keyphrases
</>
sequential decision problems
reinforcement learning
dynamic programming
active exploration
special case
influence diagrams
linear programming
training data
objective function
state space
optimal policy
sample complexity
decision theoretic